remove scripts

eval_all.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-#for model in ddgan_sd_v10 ddgan_laion2b_v2 ddgan_ddb_v1 ddgan_ddb_v2 ddgan_ddb_v3 ddgan_ddb_v4;do 
-#for model in ddgan_ddb_v2 ddgan_ddb_v3 ddgan_ddb_v4 ddgan_ddb_v5;do 
-#for model in ddgan_ddb_v4 ddgan_ddb_v6 ddgan_ddb_v7 ddgan_laion_aesthetic_v15;do 
-#for model in ddgan_ddb_v6;do 
-for model in ddgan_laion_aesthetic_v15;do 
-    if [ "$model" == "ddgan_ddb_v3" ]; then
-        bs=32
-    elif [ "$model" == "ddgan_laion_aesthetic_v15" ]; then
-        bs=32
-    elif [ "$model" == "ddgan_ddb_v6" ]; then
-        bs=32
-    elif [ "$model" == "ddgan_ddb_v4" ]; then
-        bs=16
-    else
-        bs=64
-    fi
-    sbatch --partition dc-gpu -t 360 -N 1 -n1 scripts/run_jurecadc_ddp.sh run.py test $model --cond-text=parti_prompts.txt  --batch-size=$bs --epoch=-1 --compute-clip-score --eval-name=parti;
-    sbatch --partition dc-gpu -t 360 -N 1 -n1 scripts/run_jurecadc_ddp.sh run.py test $model --fid --real-img-dir inception_statistics_coco_val2014_256x256.npz --cond-text coco_val2014_captions.txt  --batch-size=$bs --epoch=-1 --nb-images-for-fid=30000 --eval-name=coco --compute-clip-score;
-    sbatch --partition dc-gpu -t 360 -N 1 -n1 scripts/run_jurecadc_ddp.sh run.py test $model --cond-text=drawbench.txt  --batch-size=$bs --epoch=-1 --compute-clip-score --eval-name=drawbench;
-done

scripts/init.sh

@@ -1,14 +0,0 @@
-ml purge
-ml use $OTHERSTAGES
-ml Stages/2022
-ml GCC/11.2.0
-ml OpenMPI/4.1.2
-ml CUDA/11.5
-ml cuDNN/8.3.1.22-CUDA-11.5
-ml NCCL/2.12.7-1-CUDA-11.5
-ml PyTorch/1.11-CUDA-11.5
-ml Horovod/0.24
-ml torchvision/0.12.0
-source /p/home/jusers/cherti1/jureca/ccstdl/code/feed_forward_vqgan_clip/envs/jureca_2022/bin/activate
-export HOROVOD_CACHE_CAPACITY=4096
-export CUDA_VISIBLE_DEVICES=0,1,2,3

scripts/init_2020.sh

@@ -1,69 +0,0 @@
-machine=$(cat /etc/FZJ/systemname)
-if [[ "$machine" == jurecadc ]]; then
-    export CUDA_VISIBLE_DEVICES=0,1,2,3
-    #ml use $OTHERSTAGES
-    #ml Stages/2020
-    #ml GCC/9.3.0
-    #ml OpenMPI/4.1.0rc1
-    #ml CUDA/11.0
-    #ml cuDNN/8.0.2.39-CUDA-11.0
-    #ml NCCL/2.8.3-1-CUDA-11.0
-    #ml PyTorch
-    #ml Horovod/0.20.3-Python-3.8.5
-    #ml scikit
-    #source /p/project/covidnetx/environments/jureca/bin/activate 
-    ml purge
-    ml use $OTHERSTAGES
-    ml Stages/2020
-    ml GCC/10.3.0
-    ml OpenMPI/4.1.1
-    ml Horovod/0.23.0-Python-3.8.5
-    ml scikit
-    source /p/project/covidnetx/environments/jureca/bin/activate 
-fi
-if [[ "$machine" == juwelsbooster ]]; then
-    export CUDA_VISIBLE_DEVICES=0,1,2,3
-    #ml use $OTHERSTAGES
-    #ml Stages/2020
-    #ml GCC/9.3.0
-    #ml OpenMPI/4.1.0rc1
-    #ml CUDA/11.0
-    #ml cuDNN/8.0.2.39-CUDA-11.0
-    #ml NCCL/2.8.3-1-CUDA-11.0
-    #ml PyTorch
-    #ml Horovod/0.20.3-Python-3.8.5
-    #ml scikit
-
-    #ml Stages/2021
-    #ml GCC
-    #ml OpenMPI
-    #ml CUDA
-    #ml cuDNN
-    #ml NCCL
-    #ml PyTorch
-    #ml Horovod
-    #ml scikit
-
-    ml purge
-    ml use $OTHERSTAGES
-    ml Stages/2020
-    ml GCC/10.3.0
-    ml OpenMPI/4.1.1
-    ml Horovod/0.23.0-Python-3.8.5
-    ml scikit
-    source /p/project/covidnetx/environments/juwels_booster/bin/activate 
-fi
-if [[ "$machine" == jusuf ]]; then
-    ml purge
-    ml use $OTHERSTAGES
-    ml Stages/2020
-    ml GCC/9.3.0
-    ml OpenMPI/4.1.0rc1
-    ml CUDA/11.0
-    ml cuDNN/8.0.2.39-CUDA-11.0
-    ml NCCL/2.8.3-1-CUDA-11.0
-    ml PyTorch
-    ml Horovod/0.20.3-Python-3.8.5
-    #ml scikit
-    source /p/project/covidnetx/environments/jusuf/bin/activate
-fi

scripts/init_2022.sh

@@ -1,34 +0,0 @@
-machine=$(cat /etc/FZJ/systemname)
-if [[ "$machine" == jurecadc ]]; then
-    export CUDA_VISIBLE_DEVICES=0,1,2,3
-    ml purge
-    ml use $OTHERSTAGES
-    ml Stages/2022
-    ml GCC/11.2.0
-    ml OpenMPI/4.1.2
-    ml CUDA/11.5
-    ml cuDNN/8.3.1.22-CUDA-11.5
-    ml NCCL/2.12.7-1-CUDA-11.5
-    ml PyTorch/1.11-CUDA-11.5
-    ml Horovod/0.24
-    ml torchvision/0.12.0
-    source /p/project/covidnetx/environments/jureca_2022/bin/activate 
-fi
-if [[ "$machine" == juwelsbooster ]]; then
-    export CUDA_VISIBLE_DEVICES=0,1,2,3
-    ml purge
-    ml use $OTHERSTAGES
-    ml Stages/2022
-    ml GCC/11.2.0
-    ml OpenMPI/4.1.2
-    ml CUDA/11.5
-    ml cuDNN/8.3.1.22-CUDA-11.5
-    ml NCCL/2.12.7-1-CUDA-11.5
-    ml PyTorch/1.11-CUDA-11.5
-    ml Horovod/0.24
-    ml torchvision/0.12.0
-    source /p/project/covidnetx/environments/juwels_booster_2022/bin/activate 
-fi
-if [[ "$machine" == jusuf ]]; then
-    echo not supported
-fi

scripts/run_hdfml.sh

@@ -1,25 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=cstdl
-#SBATCH --nodes=8
-#SBATCH --ntasks-per-node=4
-#SBATCH --cpus-per-task=8
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu
-#SBATCH --partition=batch
-ml purge
-ml use $OTHERSTAGES
-ml Stages/2022
-ml GCC/11.2.0
-ml OpenMPI/4.1.2
-ml CUDA/11.5
-ml cuDNN/8.3.1.22-CUDA-11.5
-ml NCCL/2.12.7-1-CUDA-11.5
-ml PyTorch/1.11-CUDA-11.5
-ml Horovod/0.24
-ml torchvision/0.12.0
-source envs/hdfml/bin/activate
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-export NCCL_ASYNC_ERROR_HANDLING=1
-srun python -u $*

scripts/run_jurecadc_conda.sh

@@ -1,23 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=zam
-#SBATCH --nodes=1
-#SBATCH --ntasks-per-node=4
-#SBATCH --cpus-per-task=24
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu:4
-#SBATCH --partition=dc-gpu
-ml CUDA
-source /p/project/laionize/miniconda/bin/activate
-conda activate ddgan
-#source scripts/init_2022.sh
-#source scripts/init_2020.sh
-#source scripts/init.sh
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-#export NCCL_ASYNC_ERROR_HANDLING=1
-export NCCL_IB_TIMEOUT=50
-export UCX_RC_TIMEOUT=4s
-export NCCL_IB_RETRY_CNT=10
-export TORCH_DISTRIBUTED_DEBUG=INFO
-srun python -u $*

scripts/run_jurecadc_ddp.sh

@@ -1,20 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=zam
-#SBATCH --nodes=1
-#SBATCH --ntasks-per-node=4
-#SBATCH --cpus-per-task=24
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu:4
-#SBATCH --partition=dc-gpu
-source set_torch_distributed_vars.sh
-#source scripts/init_2022.sh
-#source scripts/init_2020.sh
-source scripts/init.sh
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-#export NCCL_ASYNC_ERROR_HANDLING=1
-export NCCL_IB_TIMEOUT=50
-export UCX_RC_TIMEOUT=4s
-export NCCL_IB_RETRY_CNT=10
-srun python -u $*

scripts/run_jusuf_ddp.sh

@@ -1,14 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=zam
-#SBATCH --nodes=1
-#SBATCH --ntasks-per-node=1
-#SBATCH --cpus-per-task=24
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu:1
-#SBATCH --partition=gpus
-source set_torch_distributed_vars.sh
-source scripts/init.sh
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-srun python -u $*

scripts/run_juwelsbooster_conda.sh

@@ -1,19 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=laionize
-#SBATCH --nodes=1
-#SBATCH --ntasks-per-node=4
-#SBATCH --cpus-per-task=24
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu:4
-#SBATCH --partition=booster
-ml CUDA
-source /p/project/laionize/miniconda/bin/activate
-conda activate ddgan
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-#export NCCL_ASYNC_ERROR_HANDLING=1
-export NCCL_IB_TIMEOUT=50
-export UCX_RC_TIMEOUT=4s
-export NCCL_IB_RETRY_CNT=10
-srun python -u $*

scripts/run_juwelsbooster_ddp.sh

@@ -1,17 +0,0 @@
-#!/bin/bash -x
-#SBATCH --account=covidnetx
-#SBATCH --nodes=4
-#SBATCH --ntasks-per-node=4
-#SBATCH --cpus-per-task=24
-#SBATCH --time=06:00:00
-#SBATCH --gres=gpu:4
-#SBATCH --partition=booster
-source set_torch_distributed_vars.sh
-#source scripts/init_2022.sh
-#source scripts/init_2020.sh
-source scripts/init.sh
-export CUDA_VISIBLE_DEVICES=0,1,2,3
-echo "Job id: $SLURM_JOB_ID"
-export TOKENIZERS_PARALLELISM=false
-export NCCL_ASYNC_ERROR_HANDLING=1
-srun python -u $*